Filters








40,939 Hits in 2.9 sec

Interactive regret minimization

Danupon Nanongkai, Ashwin Lall, Atish Das Sarma, Kazuhisa Makino
2012 Proceedings of the 2012 international conference on Management of Data - SIGMOD '12  
In this paper, we study the problem of minimizing regret ratio when the system is enhanced with interaction.  ...  Under this assumption, we develop the problem of interactive regret minimization where we fix the number of questions and tuples per question that we can display, and aim at minimizing the regret ratio  ...  We will focus on minimizing the smaller quantity u,p − u,q u,p which we call the regret ratio. We consider the following problem of interactive regret minimization with r questions of size s.  ... 
doi:10.1145/2213836.2213850 dblp:conf/sigmod/NanongkaiLSM12 fatcat:fiegdpofbnfzreumq4v22kpsnq

Sorting-based Interactive Regret Minimization [article]

Jiping Zheng, Chen Chen
2020 arXiv   pre-print
In this paper, we study how to enhance current interactive regret minimization query by sorting mechanism.  ...  Existing researches verify that the regret ratio can be much decreased when interaction is available.  ...  [14] first enhance traditional regret minimization sets by user interaction.  ... 
arXiv:2006.10949v1 fatcat:lkhz5d5b3zb77hnmjy5b2rlwqi

Generalized Bandit Regret Minimizer Framework in Imperfect Information Extensive-Form Game [article]

Linjian Meng, Yang Gao
2022 arXiv   pre-print
To learn NE, the regret minimizer is required to estimate the full-feedback loss gradient ℓ^t by v(z^t) and minimize the regret.  ...  It presents a theoretical framework for the design and the modular analysis of the bandit regret minimization methods.  ...  Regret Minimization In this subsection, we introduce the regret minimization methods and the interactive bandit-feedback setting.  ... 
arXiv:2203.05920v2 fatcat:ifttsm7jrnex7da3qzj4qy4pe4

Model-Free Online Learning in Unknown Sequential Decision Making Problems and Games [article]

Gabriele Farina, Tuomas Sandholm
2021 arXiv   pre-print
Regret minimization has proved to be a versatile tool for tree-form sequential decision making and extensive-form games.  ...  We give the first, to our knowledge, regret-minimization algorithm that guarantees sublinear regret with high probability even when requirement (i) – and thus also (ii) – is dropped.  ...  At a high level, the construction of our interactive bandit regret minimizer works as follows.  ... 
arXiv:2103.04539v1 fatcat:3s5z2crajvamplbizn65dwn5ky

From Optimization to Regret Minimization and Back Again

Ioannis C. Avramopoulos, Jennifer Rexford, Robert E. Schapire
2008 USENIX Symposium on Operating Systems Design and Implementation  
In this paper, we propose a different framework for adaptive routing decisions based on regret-minimizing online learning algorithms.  ...  However, previous approaches for making Internet routing adaptive based on optimizing network-wide objectives are not suited for an environment in which autonomous and possibly malicious entities interact  ...  Interaction of regret-minimizing algorithms: Previous work has studied whether zero-regret algorithms in a repeated game setting converge to a Nash equilibrium.  ... 
dblp:conf/osdi/AvramopoulosRS08 fatcat:3mxq6bxavvanrd7gagmaab5kby

The ecological rationality of decision criteria

Paolo Galeazzi, Alessandro Galeazzi
2020 Synthese  
Minimizing regret also finds some evolutionary justifications in our results, while maximin seems to be always disadvantaged by differential selection.  ...  This is different from the results obtained for interactive decision making in Sect. 5, where linear regret minimization was mostly superior to nonlinear regret minimization.  ...  Nonlinear regret minimization An equally reasonable version of regret minimization is the one we call nonlinear regret minimization.  ... 
doi:10.1007/s11229-020-02785-y fatcat:tvw4l75zg5frpmmwb32a3bhaci

Combining Counterfactual Regret Minimization with Information Gain to Solve Extensive Games with Imperfect Information [article]

Chen Qiu, Xuan Wang, Tianzi Ma, Yaojun Wen, Jiajia Zhang
2021 arXiv   pre-print
Counterfactual regret Minimization (CFR) is an effective algorithm for solving extensive games with imperfect information (IIEG).  ...  Experimentally, The results demonstrate that this approach can not only effectively reduce the number of interactions with the environment, but also find an approximate NE.  ...  Counterfactual Regret Minimization The counterfactual regret minimization (CFR) algorithm (Zinkevich et al. 2007; , which converges to Nash equilibrium by constantly iterating to reduce regrets, has been  ... 
arXiv:2110.07892v1 fatcat:xopyt5kxmvhbbo4tlvwpoegsnu

Let's Collaborate: Regret-based Reactive Synthesis for Robotic Manipulation [article]

Karan Muvvala, Peter Amorese, Morteza Lahijanian
2022 arXiv   pre-print
We identify an appropriate definition for regret and develop regret-minimizing synthesis framework that enables the robot to seek cooperation when possible while preserving task completion guarantees.  ...  As robots gain capabilities to enter our human-centric world, they require formalism and algorithms that enable smart and efficient interactions.  ...  In regret games, instead of trying to minimize the total cost, the objective is to minimize regret.  ... 
arXiv:2203.06861v1 fatcat:m2m7zb4fi5dmrmcobc2mcea4le

Evolutionary Dynamics of Regret Minimization [chapter]

Tomas Klos, Gerrit Jan van Ahee, Karl Tuyls
2010 Lecture Notes in Computer Science  
Using these equations we can easily investigate parameter settings and analyze the dynamics of multiple concurrently learning agents using regret minimization.  ...  More precisely, we formally derive the evolutionary dynamics of the Regret Minimization polynomial weights learning algorithm, which will be described by a system of differential equations.  ...  Regret Minimization (RM), these dynamics are still unknown.  ... 
doi:10.1007/978-3-642-15883-4_6 fatcat:wvvf2avoivffbm6wp6cqqhezgi

Optimal Set Recommendations Based on Regret

Paolo Viappiani, Craig Boutilier
2009 International Joint Conference on Artificial Intelligence  
This new criterion extends the mathematical notion of maximum regret used in decision theory and preference elicitation to sets. We develop computational procedures for computing setwise max regret.  ...  Thus setwise max regret acts both as guarantee on the quality of our recommendations and as a driver for further utility elicitation.  ...  Fig. 4 shows the maximum regret of the recommended product at each stage of the interaction.  ... 
dblp:conf/ijcai/ViappianiB09 fatcat:4f7qfejodvaxhigqfygn22nsae

An Intrusion Detection Scheme Based on Repeated Game in Smart Home

Rui Zhang, Hui Xia, Shu-shu Shao, Hang Ren, Shuai Xu, Xiang-guo Cheng
2020 Mobile Information Systems  
Secondly, we use the regret minimization algorithm to determine the mixed strategy Nash equilibrium of the one-order game and then take a severe punishment strategy to domesticate malicious attackers.  ...  the optimal strategy for each round of interaction between the attacker and intrusion detection system by using the regret minimization algorithm.  ...  Table 5 compares the payoffs of player A and player B when player A adopts five strategies: regret minimization strategy (Regret), ALL-R, ALL-P, ALL-S, and Winner, while player B adopts a regret minimization  ... 
doi:10.1155/2020/8844116 doaj:87db992258bc48aabdbfa8459f3fb43d fatcat:okkupgrbpbgxxl2pwzmqvffn2u

Framing Effects on Strategic Information Design under Receiver Distrust and Unknown State [article]

Doris E. M. Brown, Venkata Sriram Siddhardh Nadendla
2021 arXiv   pre-print
Furthermore, we also investigate trust dynamics at the receiver, under the assumption that the receiver minimizes regret in hindsight.  ...  We will also develop a better trust dynamics model in the repeated interaction setting where the receiver minimizes cumulative regret, as opposed to instantaneous, one-shot regret in our paper.  ...  Instead, he decreases his trust by a finite value ε ∈ [0, 1] to mitigate Alice's influence in subsequent interactions and minimize Bob's cumulative regret over time.  ... 
arXiv:2005.05516v2 fatcat:aajpyxuz4jgaflg4xtftqrfkty

Evolutionary Dynamics and Phi-Regret Minimization in Games

Georgios Piliouras, Mark Rowland, Shayegan Omidshafiei, Romuald Elie, Daniel Hennes, Jerome Connor, Karl Tuyls
2022 The Journal of Artificial Intelligence Research  
It is well known that regret-minimizing algorithms converge to certain classes of equilibria in games; however, traditional forms of regret used in game theory predominantly consider baselines that permit  ...  We conclude by providing empirical evidence of Φ-regret minimization by RD in some larger games, hinting at further opportunity for Φ-regret based study of such algorithms from both a theoretical and empirical  ...  Players interacting in a two-player game using algorithms that minimize swap regret are guaranteed to converge to the set of correlated equilibria in time-average, a stronger notion that the coarse correlated  ... 
doi:10.1613/jair.1.13187 fatcat:hpeo5bx4ujeovn7jfwxrrkk3hi

Evolutionary Dynamics and Φ-Regret Minimization in Games [article]

Georgios Piliouras, Mark Rowland, Shayegan Omidshafiei, Romuald Elie, Daniel Hennes, Jerome Connor, Karl Tuyls
2021 arXiv   pre-print
It is well-known that regret-minimizing algorithms converge to certain classes of equilibria in games; however, traditional forms of regret used in game theory predominantly consider baselines that permit  ...  We conclude by providing empirical evidence of Φ-regret minimization by RD in some larger games, hinting at further opportunity for Φ-regret based study of such algorithms from both a theoretical and empirical  ...  Players interacting in a two-player game using algorithms that minimize swap regret are guaranteed to converge to the set of correlated equilibria in time-average, a stronger notion that the coarse correlated  ... 
arXiv:2106.14668v1 fatcat:wrmagg2kyvegdjdxnsd7k5t42i

Weighing the techniques for data optimization in a database [article]

Anagha Radhakrishnan
2022 arXiv   pre-print
Interactive regret minimization (IRM) IRM is obtained by including personalization in RMS. It involves the user in the search process through multiple rounds of interaction.  ...  REGRET MINIMIZATION K-representative regret minimizing query (k-regret) is a useful operator for supporting multi-criteria decision-making.  ... 
arXiv:2203.09236v1 fatcat:fnscups23bgvvoi6flw7r3aiwm
« Previous Showing results 1 — 15 out of 40,939 results